*Given sufficient data, according to the Universal Approximation Theorem, a neur... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

joe_the_user on May 28, 2018 | parent | context | favorite | on: Empiricism and the limits of gradient descent

Given sufficient data, according to the Universal Approximation Theorem, a neural network can learn to model physics.

The ability of a system of linked functions to approximate any continuous function seems rather far from the ability to "learn modern physics".

It would seem like knowing modern physics would involve symbolic calculations rather than just approximating the behavior of any system.

AstralStorm on May 28, 2018 [–]

A lot of physics is functions with singularities. ANN can only approximate these to a specified limit...

I want to see a neutral network that correctly solves SAT-3.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact